This paper proposes Mem-GF, a memory-efficient graph filtering-based collaborative filtering method that approximates polynomial graph filters using Krylov subspaces, achieving significant memory savi…

The paper introduces a novel realization-level privacy filtering approach that improves utility in differentially private data release by accounting for actual leakage rather than worst-case per-round…

This paper proposes a mood-conditioned ranking framework for music recommendation systems using user affective signals in the energy-valence space.

This paper comparatively analyzes two automatic label error detection methods, Confident Learning and Dataset Cartography, demonstrating that targeted data filtering significantly improves model perfo…

This paper develops scalable methods for time-series analysis using tensor algebra in factorial hidden Markov models, improving computational performance and enabling analysis of large systems.

A Wave-U-Net model is trained to extract a fundamental waveform from input speech signals for accurate and robust instantaneous pitch estimation.

A six-pole dual-band bandpass filter is designed and simulated using FASOLR microstrip planar structure, producing two passbands centered at approximately 2.2 GHz and 2.4 GHz.

The paper introduces a Privacy Policy Enforcement (PPE) framework using dual one-class density estimators to detect contextual data leakage in Retrieval-Augmented Generation (RAG) systems, achieving h…

WaveFilter is a novel, training-free framework that uses wavelet transforms to efficiently filter critical tokens in the KV cache, significantly improving the long-context performance of Diffusion LLM…

This paper reformulates cascaded second-order filtering as a block-tridiagonal linear system and develops parallel solution algorithms, achieving high performance on SIMD cores, multi-core CPUs, and G…

This paper presents methods for ranking and unranking permutations avoiding a pattern of length three in lexicographic or colexicographic order.

The paper introduces 'contrastive privacy,' a formal, model-agnostic, and quantitative method for evaluating the semantic success of AI-based sanitization across multiple media modalities.

Proposed DDMSR framework for multi-modal sequential recommendation using graph-based feature denoising and frequency-domain sequence denoising, and multi-modal contrastive alignment objective.

This paper introduces a new way to represent finite posets as subwords of finite words in categories, and characterizes the monic categories that admit this representation.

This paper introduces Spectral Attention and Graph Convolutional Attention (GCA) for denoising graphs, which outperforms linear attention and provably utilizes the input graph spectrum.

This paper introduces a new R package for Non-negative Matrix Factorization (NMF) and compares its performance systematically with two other R packages using real-world data.

This paper demonstrates that in-domain pretraining of BERT significantly improves the detection of DNS exfiltration, particularly in maintaining a low false positive rate.

This paper proposes a data-driven method for automatic blind audio equalization using a deep neural network and semantic embeddings.

The paper introduces retraining-free frameworks (Meow2X and TRNE) that mechanistically localize and suppress toxicity within language models by analyzing activation differences, achieving safety impro…

This paper presents the topology-independent distributed multichannel Wiener filter (TI-dMWF) algorithm for distributed node-specific signal estimation in wireless acoustic sensor networks, enabling o…